Especially for athletes, the proper fit of footwear is critical for both, health and performance. For the selection of good fitting shoes, the shoe size is the only available metric visible to consumers. However, the shoe size is commonly determined by the foot length alone, not taking the complex and individual shape of human feet into consideration (Reinschmidt & Nigg 2000). In this work, the last length specifying the shoe length is estimated by applying regression methods using 2D metrics describing the shape of human feet. These measurements include lengths, widths, heights and circumferences. The accuracy of predictions for different feature subsets is compared. By this, first insights into the influence of additional metrics besides the foot length on the selection of the proper shoe size are gained.
© Copyright 2018 Sportinformatik XII. 12. Symposium der dvs-Sektion "Sportinformatik und Sporttechnologie" vom 5.-7. September 2018 in Garching. Abstracts.. Veröffentlicht von Feldhaus, Ed. Czwalina. Alle Rechte vorbehalten.